Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Even with annotations declaring readOnly/openWorld/idempotent hints, the description adds significant behavioral context: it fans out across two services, degrades gracefully on partial failures, and warns that bundlephobia's first measurement can take 5-30 seconds with sources_failed listing timeouts. It also discloses the return structure and NPM-only limitation, going well beyond the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is dense and information-rich, with a logical flow: composite purpose, use case, return fields, ecosystem scope, failure handling. It is not as terse as the calibration high example, but every sentence serves a purpose and there is no repetition or fluff. The front-loading is excellent, starting with the core purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the absence of an output schema, the description thoroughly covers return values by listing the summary block fields (is_latest, license, published_at, advisory_count, bundle_kb_min, bundle_kb_gz, dependency_count, has_esm, tree_shakeable) as well as per-advisory detail, links, and alternative versions. It also addresses latency, failure behavior, ecosystem scope, and version defaults, making it complete for this complex composite tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema already provides 100% coverage with clear descriptions for both 'package' and 'version'. The tool description does not add further parameter-level meaning beyond what the schema states, so the baseline of 3 applies. The mention of 'new version' while describing latency is tangential and does not substantially enrich parameter semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states exactly what the tool does: a composite 'should I add this npm package' check that fans out to deps.dev and bundlephobia. It uses specific verbs ('fans out', 'returns') and clearly identifies the resource (npm packages) and the data collected. It also distinguishes itself from siblings by highlighting its composite nature and NPM-only scope.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly says 'Use whenever an agent asks "is X safe / popular / small" or "what does adding lodash cost me"', giving clear triggers. It also provides an exclusion: 'NPM ecosystem only in v1; PyPI / Maven / Cargo / Go fall under deps.dev:version directly.' This tells the agent when not to use this tool and what to use instead, satisfying the when/when-not/alternatives requirement.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.